simready-foundation-conform-fet-024-newton
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources to determine necessary asset repairs, creating an attack surface where malicious data could influence agent behavior.
- Ingestion points: The skill processes external profile TOML files, validation reports, and user requests to identify repair requirements (SKILL.md).
- Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions embedded within the ingested reports.
- Capability inventory: The agent is instructed to read internal manifests, modify assets in staged or in-place locations, and execute validation gates (SKILL.md).
- Sanitization: No sanitization, escaping, or validation of the content within the reports is specified before the agent acts upon the data.
Audit Metadata